Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

Université Laval

$19,000.00

Case-based reasoning for making decisions in dynamic game environments

EF 2012-13

Résumé
In this research project, I will investigate how Case-Based Reasoning (CBR) techniques can contribute to the development of decision modules for dynamic game environments. My objectives are a) to determine the potential benefits of using CBR techniques for capturing and reusing game episodes, b) to study how CBR techniques can contribute to the development of interesting and efficient game AI decision schemes, and c) to address technical limitations of current CBR techniques to make them more suitable for dynamic and uncertain environments like real-time games. Current technologies for implementing nonplayer characters (NPC) in games mostly rely on finite state machines (FSM), a static structure that can be quite extensive and difficult to edit for complex games. We believe that CBR, exploited as a dynamic decision scheme, can significantly contribute to game development by facilitating the design of elaborate behaviours. CBR consists of reusing past experiences to solve new problems. For this project, we foresee CBR as a mean to efficiently store and encode game episodes that can be reused for player modeling or behaviour cloning. However, to be exploited by a CBR system, episodes have to be properly encoded and stored in a case base. Due to the sequential nature of games, some issues have to be tackled for the structuring of the episodes. Technical issues to be addressed in this project are : - how to conduct sequences of decisions using CBR; - how to adapt the reasoning cycle to different decision timelines; and - how to take into account implicit interactions with human players. This proposal builds on a research effort we are conducting with some industrial partners and is an initiative to investigate longer term issues to be addressed in support of this collaboration.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
315794-2009
Name nom
Lamontagne, Luc
Department département
Informatique et de génie logiciel
Organization id
51
Institution établissement
Université Laval
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2009
Award amount
19000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Partie
4
Nb partie
5
Application title
Case-based reasoning for making decisions in dynamic game environments
Keyword
NSERC
Application summary
In this research project, I will investigate how Case-Based Reasoning (CBR) techniques can contribute to the development of decision modules for dynamic game environments. My objectives are a) to determine the potential benefits of using CBR techniques for capturing and reusing game episodes, b) to study how CBR techniques can contribute to the development of interesting and efficient game AI decision schemes, and c) to address technical limitations of current CBR techniques to make them more suitable for dynamic and uncertain environments like real-time games. Current technologies for implementing nonplayer characters (NPC) in games mostly rely on finite state machines (FSM), a static structure that can be quite extensive and difficult to edit for complex games. We believe that CBR, exploited as a dynamic decision scheme, can significantly contribute to game development by facilitating the design of elaborate behaviours. CBR consists of reusing past experiences to solve new problems. For this project, we foresee CBR as a mean to efficiently store and encode game episodes that can be reused for player modeling or behaviour cloning. However, to be exploited by a CBR system, episodes have to be properly encoded and stored in a case base. Due to the sequential nature of games, some issues have to be tackled for the structuring of the episodes. Technical issues to be addressed in this project are : - how to conduct sequences of decisions using CBR; - how to adapt the reasoning cycle to different decision timelines; and - how to take into account implicit interactions with human players. This proposal builds on a research effort we are conducting with some industrial partners and is an initiative to investigate longer term issues to be addressed in support of this collaboration.